Triple
T30166491
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Вознесенский проспект |
E766805
|
entity |
| Predicate | расположение |
P25921
|
FINISHED |
| Object | центр Санкт-Петербурга |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: центр Санкт-Петербурга | Statement: [Вознесенский проспект, расположение, центр Санкт-Петербурга]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: расположение Context triple: [Вознесенский проспект, расположение, центр Санкт-Петербурга]
-
A.
propertyLocation
chosen
Indicates the geographical place or address where a property is situated or found.
-
B.
расположенаНа
Indicates that one entity is located on the surface or area of another entity.
-
C.
locates
Indicates that one entity determines, specifies, or identifies the position or place of another entity in space or within a given context.
-
D.
luogo
Indicates that something is located, occurs, or exists in a particular place or location.
-
E.
locatedAlong
Indicates that one entity is situated adjacent to, or running beside, the length or course of another linear feature (such as a road, river, or railway).
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69f2247a968881909d79c18f2bfcb275 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f67f073dbc8190a42f4c71ad2f7de3 |
completed | May 2, 2026, 10:47 p.m. |
| PD | Predicate disambiguation | batch_69f673c7a4588190837854f3ef61e6bf |
completed | May 2, 2026, 9:59 p.m. |
Created at: April 29, 2026, 7:23 p.m.